Yeah – I think so… solutions so far: 1) Another agent to review web learnings for common sense
2) Require two sources that match a learning before accepting
3) Limit sites to review via programatic search
AUTOMATION
-
Agent AI Solutions: Common Sense Review and Source Validation
By
–
-
AI-Powered Strategy for Identifying Engaged Social Media Users
By
–
My AI is telling me that getting doomers to reply to my tweets is an effective way to identi
-
AI Agent Release Announcement and Substack Signup
By
–
"If you want to be notified of when I release this AI agent into the wild, subscribe to my substack below!" jk I don't have one
-
LangChain Task Execution with Separate OpenAI Calls
By
–
Oh yeah, the thought/observation is using @langchain
, which I'm using to execute each tasks. Separate OpenAI call for task creation/reprioritization -
AI Agent with Search and Action Capabilities Development
By
–
Yep, and it's generating questions by researching the task online. Only has search functionality for now, but can take actions w a few lines of code added.
-
Removing humans from AI automation processes
By
–
This was part of the motivation! But wondered if I could cut the human out of it.
-
Generative AI at Work: Best of Human and AI Collaboration
By
–
#GenerativeAI at work . . . the best of human + #AI
-
Task Storage in Pinecone for AI Agent Context
By
–
More or less. It’s also storing task/result in pinecone and tapping into it for context in future tasks.
-
AI Agents with Email and Service Provider Integration Capabilities
By
–
If I gave it email capabilities and a list of trusted service providers (lawyers, accountants, etc). I don’t see why not.
-
ChatGPT Plugins and Zapier NLA Integration Next Steps
By
–
Haha yep. Next step is ChatGPT plug-ins and Zapier NLA I guess